1 / 39

Fitting

Fitting. Fitting. We’ve learned how to detect edges, corners, blobs. Now what? We would like to form a higher-level, more compact representation of the features in the image by grouping multiple features according to a simple model. 9300 Harris Corners Pkwy, Charlotte, NC. Fitting.

raina
Download Presentation

Fitting

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Fitting

  2. Fitting • We’ve learned how to detect edges, corners, blobs. Now what? • We would like to form a higher-level, more compact representation of the features in the image by grouping multiple features according to a simple model 9300 Harris Corners Pkwy, Charlotte, NC

  3. Fitting • Choose a parametric model to represent a set of features simple model: circles simple model: lines complicated model: car Source: K. Grauman

  4. Fitting: Issues • Noise in the measured feature locations • Extraneous data: clutter (outliers), multiple lines • Missing data: occlusions Case study: Line detection

  5. Fitting: Overview • If we know which points belong to the line, how do we find the “optimal” line parameters? • Least squares • What if there are outliers? • Robust fitting, RANSAC • What if there are many lines? • Voting methods: RANSAC, Hough transform • What if we’re not even sure it’s a line? • Model selection

  6. Least squares line fitting • Data: (x1, y1), …, (xn, yn) • Line equation: yi = mxi + b • Find (m, b) to minimize y=mx+b (xi, yi) Normal equations: least squares solution to XB=Y

  7. Problem with “vertical” least squares • Not rotation-invariant • Fails completely for vertical lines

  8. Total least squares • Distance between point (xi, yi) and lineax+by=d (a2+b2=1): |axi + byi – d| ax+by=d Unit normal: N=(a, b) (xi, yi)

  9. Total least squares • Distance between point (xi, yi) and lineax+by=d (a2+b2=1): |axi + byi – d| • Find (a, b, d) to minimize the sum of squared perpendicular distances ax+by=d Unit normal: N=(a, b) (xi, yi)

  10. Total least squares • Distance between point (xi, yi) and lineax+by=d (a2+b2=1): |axi + byi – d| • Find (a, b, d) to minimize the sum of squared perpendicular distances ax+by=d Unit normal: N=(a, b) (xi, yi) Solution to (UTU)N = 0, subject to ||N||2 = 1: eigenvector of UTUassociated with the smallest eigenvalue (least squares solution to homogeneous linear systemUN = 0)

  11. Total least squares second moment matrix

  12. Total least squares second moment matrix N = (a, b)

  13. Least squares as likelihood maximization • Generative model: line points are sampled independently and corrupted by Gaussian noise in the direction perpendicular to the line ax+by=d (u, v) ε (x, y) point on the line normaldirection noise:sampled from zero-meanGaussian withstd. dev. σ

  14. Log-likelihood: Least squares as likelihood maximization • Generative model: line points are sampled independently and corrupted by Gaussian noise in the direction perpendicular to the line ax+by=d (u, v) ε (x, y) Likelihood of points given line parameters (a, b, d):

  15. Least squares: Robustness to noise • Least squares fit to the red points:

  16. Least squares: Robustness to noise • Least squares fit with an outlier: Problem: squared error heavily penalizes outliers

  17. Robust estimators • General approach: find model parameters θ that minimizeri(xi, θ) – residual of ith point w.r.t. model parametersθρ – robust function with scale parameter σ The robust function ρ behaves like squared distance for small values of the residual u but saturates for larger values of u

  18. Choosing the scale: Just right The effect of the outlier is minimized

  19. Choosing the scale: Too small The error value is almost the same for everypoint and the fit is very poor

  20. Choosing the scale: Too large Behaves much the same as least squares

  21. Robust estimation: Details • Robust fitting is a nonlinear optimization problem that must be solved iteratively • Least squares solution can be used for initialization • Adaptive choice of scale: approx. 1.5 times median residual (F&P, Sec. 15.5.1)

  22. RANSAC • Robust fitting can deal with a few outliers – what if we have very many? • Random sample consensus (RANSAC): Very general framework for model fitting in the presence of outliers • Outline • Choose a small subset of points uniformly at random • Fit a model to that subset • Find all remaining points that are “close” to the model and reject the rest as outliers • Do this many times and choose the best model M. A. Fischler, R. C. Bolles. Random Sample Consensus: A Paradigm for Model Fitting with Applications to Image Analysis and Automated Cartography. Comm. of the ACM, Vol 24, pp 381-395, 1981.

  23. RANSAC for line fitting example Source: R. Raguram

  24. RANSAC for line fitting example Least-squares fit Source: R. Raguram

  25. RANSAC for line fitting example • Randomly select minimal subset of points Source: R. Raguram

  26. RANSAC for line fitting example • Randomly select minimal subset of points • Hypothesize a model Source: R. Raguram

  27. RANSAC for line fitting example • Randomly select minimal subset of points • Hypothesize a model • Compute error function Source: R. Raguram

  28. RANSAC for line fitting example • Randomly select minimal subset of points • Hypothesize a model • Compute error function • Select points consistent with model Source: R. Raguram

  29. RANSAC for line fitting example • Randomly select minimal subset of points • Hypothesize a model • Compute error function • Select points consistent with model • Repeat hypothesize-and-verify loop Source: R. Raguram

  30. RANSAC for line fitting example • Randomly select minimal subset of points • Hypothesize a model • Compute error function • Select points consistent with model • Repeat hypothesize-and-verify loop Source: R. Raguram

  31. RANSAC for line fitting example Uncontaminated sample • Randomly select minimal subset of points • Hypothesize a model • Compute error function • Select points consistent with model • Repeat hypothesize-and-verify loop Source: R. Raguram

  32. RANSAC for line fitting example • Randomly select minimal subset of points • Hypothesize a model • Compute error function • Select points consistent with model • Repeat hypothesize-and-verify loop Source: R. Raguram

  33. RANSAC for line fitting • Repeat N times: • Draw s points uniformly at random • Fit line to these s points • Find inliers to this line among the remaining points (i.e., points whose distance from the line is less than t) • If there are d or more inliers, accept the line and refit using all inliers

  34. Choosing the parameters • Initial number of points s • Typically minimum number needed to fit the model • Distance threshold t • Choose t so probability for inlier is p (e.g. 0.95) • Zero-mean Gaussian noise with std. dev. σ: t2=3.84σ2 • Number of samples N • Choose N so that, with probability p, at least one random sample is free from outliers (e.g. p=0.99) (outlier ratio: e) Source: M. Pollefeys

  35. Choosing the parameters • Initial number of points s • Typically minimum number needed to fit the model • Distance threshold t • Choose t so probability for inlier is p (e.g. 0.95) • Zero-mean Gaussian noise with std. dev. σ: t2=3.84σ2 • Number of samples N • Choose N so that, with probability p, at least one random sample is free from outliers (e.g. p=0.99) (outlier ratio: e) Source: M. Pollefeys

  36. Choosing the parameters • Initial number of points s • Typically minimum number needed to fit the model • Distance threshold t • Choose t so probability for inlier is p (e.g. 0.95) • Zero-mean Gaussian noise with std. dev. σ: t2=3.84σ2 • Number of samples N • Choose N so that, with probability p, at least one random sample is free from outliers (e.g. p=0.99) (outlier ratio: e) Source: M. Pollefeys

  37. Choosing the parameters • Initial number of points s • Typically minimum number needed to fit the model • Distance threshold t • Choose t so probability for inlier is p (e.g. 0.95) • Zero-mean Gaussian noise with std. dev. σ: t2=3.84σ2 • Number of samples N • Choose N so that, with probability p, at least one random sample is free from outliers (e.g. p=0.99) (outlier ratio: e) • Consensus set size d • Should match expected inlier ratio Source: M. Pollefeys

  38. Adaptively determining the number of samples • Inlier ratio e is often unknown a priori, so pick worst case, e.g. 50%, and adapt if more inliers are found, e.g. 80% would yield e=0.2 • Adaptive procedure: • N=∞, sample_count =0 • While N >sample_count • Choose a sample and count the number of inliers • Set e = 1 – (number of inliers)/(total number of points) • Recompute N from e: • Increment the sample_count by 1 Source: M. Pollefeys

  39. RANSAC pros and cons • Pros • Simple and general • Applicable to many different problems • Often works well in practice • Cons • Lots of parameters to tune • Doesn’t work well for low inlier ratios (too many iterations, or can fail completely) • Can’t always get a good initialization of the model based on the minimum number of samples

More Related